Inception releases Mercury 3 diffusion LLM at 1,068 tokens per second
Original title: Inception Releases Mercury 3 Diffusion LLM at 1,068 Tokens per Second
The page body is a cookie banner, so only the stated generation speed is available, not architecture or availability.
MarkTechPost's headline says Inception released Mercury 3, a diffusion language model, and cites a generation rate of 1,068 tokens per second. The fetched page contains only a cookie-consent notice, so no model size, benchmark, license, or availability details are in the text.
Unconfirmed: The token rate is stated only in the headline; the article body was not available.
- The headline names Inception and Mercury 3.
- The stated rate is 1,068 tokens per second.
- No architecture, weights, or release terms appear in the captured page.
From the original article
14 min read at marktechpost.comInception released Mercury 3, a diffusion LLM it says runs at 1,068 tokens per second with a 1M-token context. On Inception’s own table it leads GPT-6 Luna and Claude Haiku 5. 5 on 8 of 12 benchmarks.
By Jean-marc Mommessin · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.